Staff Research Engineer - Multimodal Generative Modelling

Synthesia is seeking a Staff Research Engineer specializing in multimodal generative modeling to join their remote team. In this role, you will focus on developing advanced voice models that can generate text and audio simultaneously, enhancing user interaction by enabling natural conversations without the typical turn-taking interruptions. You will collaborate closely with the voice lead and video teams, contributing to the broader vision of creating human-interactive models that respond to user emotions and actions. The position requires a strong background in research and development, particularly in voice technology, and the ability to propose innovative research directions. While specific qualifications are not mentioned, the role is likely suited for experienced professionals with a solid understanding of AI and multimodal systems. The working arrangement is fully remote, allowing for flexibility in your work environment. This opportunity is ideal for individuals passionate about advancing AI technology and improving communication in business settings.